English

Clustering is Efficient for Approximate Maximum Inner Product Search

Machine Learning 2015-12-01 v3 Computation and Language Machine Learning

Abstract

Efficient Maximum Inner Product Search (MIPS) is an important task that has a wide applicability in recommendation systems and classification with a large number of classes. Solutions based on locality-sensitive hashing (LSH) as well as tree-based solutions have been investigated in the recent literature, to perform approximate MIPS in sublinear time. In this paper, we compare these to another extremely simple approach for solving approximate MIPS, based on variants of the k-means clustering algorithm. Specifically, we propose to train a spherical k-means, after having reduced the MIPS problem to a Maximum Cosine Similarity Search (MCSS). Experiments on two standard recommendation system benchmarks as well as on large vocabulary word embeddings, show that this simple approach yields much higher speedups, for the same retrieval precision, than current state-of-the-art hashing-based and tree-based methods. This simple method also yields more robust retrievals when the query is corrupted by noise.

Keywords

Cite

@article{arxiv.1507.05910,
  title  = {Clustering is Efficient for Approximate Maximum Inner Product Search},
  author = {Alex Auvolat and Sarath Chandar and Pascal Vincent and Hugo Larochelle and Yoshua Bengio},
  journal= {arXiv preprint arXiv:1507.05910},
  year   = {2015}
}

Comments

10 pages, Under review at ICLR 2016

R2 v1 2026-06-22T10:15:48.661Z